Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2572 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.4190. Min Act: -0.0000

Data Index: 375581 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.4121. Min Act: -0.0000

Data Index: 491211 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1209737 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1407463 (Python Code)

Max Activating Token Index: 427

Text #4

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1254511 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3868. Min Act: -0.0000

Data Index: 760899 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1642257 (Python Code)

Max Activating Token Index: 603

Text #7

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3896. Min Act: -0.0000

Data Index: 752955 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3675. Min Act: -0.0000

Data Index: 617625 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1408207 (Python Code)

Max Activating Token Index: 671

Text #10

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3650. Min Act: -0.0000

Data Index: 503148 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3408. Min Act: -0.0000

Data Index: 186285 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1502389 (Python Code)

Max Activating Token Index: 778

Text #13

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1000653 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1613445 (Python Code)

Max Activating Token Index: 846

Text #15

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1556525 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1451144 (Python Code)

Max Activating Token Index: 770

Text #17

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1570266 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1517511 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 0.4190. Min Range: -0.4190

Max Act: 0.3049. Min Act: -0.0000

Data Index: 940486 (C4 (Web Text))

Max Activating Token Index: 988